Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2116 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6650. Min Act: -0.0000

Data Index: 896844 (The Pile)

Max Activating Token Index: 369

Text #1

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6953. Min Act: -0.0000

Data Index: 774952 (The Pile)

Max Activating Token Index: 523

Text #2

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6616. Min Act: -0.0000

Data Index: 1638648 (The Pile)

Max Activating Token Index: 915

Text #3

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6531. Min Act: -0.0000

Data Index: 615086 (The Pile)

Max Activating Token Index: 541

Text #4

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6497. Min Act: -0.0000

Data Index: 1447379 (The Pile)

Max Activating Token Index: 497

Text #5

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6526. Min Act: -0.0000

Data Index: 762645 (The Pile)

Max Activating Token Index: 741

Text #6

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6419. Min Act: -0.0000

Data Index: 785226 (The Pile)

Max Activating Token Index: 335

Text #7

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6577. Min Act: -0.0000

Data Index: 484395 (The Pile)

Max Activating Token Index: 507

Text #8

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6018. Min Act: -0.0000

Data Index: 378102 (The Pile)

Max Activating Token Index: 312

Text #9

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6331. Min Act: -0.0000

Data Index: 922287 (The Pile)

Max Activating Token Index: 470

Text #10

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5966. Min Act: -0.0000

Data Index: 120154 (The Pile)

Max Activating Token Index: 39

Text #11

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6146. Min Act: -0.0000

Data Index: 342390 (The Pile)

Max Activating Token Index: 925

Text #12

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1627768 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5977. Min Act: -0.0000

Data Index: 1102359 (The Pile)

Max Activating Token Index: 99

Text #14

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5736. Min Act: -0.0000

Data Index: 213658 (The Pile)

Max Activating Token Index: 131

Text #15

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5797. Min Act: -0.0000

Data Index: 1481220 (The Pile)

Max Activating Token Index: 793

Text #16

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5965. Min Act: -0.0000

Data Index: 414460 (The Pile)

Max Activating Token Index: 914

Text #17

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5742. Min Act: -0.0000

Data Index: 1252943 (The Pile)

Max Activating Token Index: 177

Text #18

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6534. Min Act: -0.0000

Data Index: 968944 (The Pile)

Max Activating Token Index: 255

Text #19

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5688. Min Act: -0.0000

Data Index: 1191537 (The Pile)

Max Activating Token Index: 245